The DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Machine Learning of Toxicological Big Data Enables Read-Across Structure Activity Relationships (RASAR) Outperforming Animal Test Reproducibility
Open accessAbstract
Earlier we created a chemical hazard database via natural language processing of dossiers submitted to the European Chemical Agency with approximately 10 000 chemicals. We identified repeat OECD guideline tests to establish reproducibility of acute oral and dermal toxicity, eye and skin irritation, mutagenicity and skin sensitization. Based on 350-700+ chemicals each, the probability that an OECD guideline animal test would output the same result in a repeat test was 78%-96% (sensitivity 50%-87%). An expanded database with more than 866 000 chemical properties/hazards was used as training data and to model health hazards and chemical properties. The constructed models automate and extend the read-across method of chemical classification. The novel models called RASARs (read-across structure activity relationship) use binary fingerprints and Jaccard distance to define chemical similarity. A large chemical similarity adjacency matrix is constructed from this similarity metric and is used to derive feature vectors for supervised learning. We show results on 9 health hazards from 2 kinds of RASARs-"Simple" and "Data Fusion". The "Simple" RASAR seeks to duplicate the traditional read-across method, predicting hazard from chemical analogs with known hazard data. The "Data Fusion" RASAR extends this concept by creating large feature vectors from all available property data rather than only the modeled hazard. Simple RASAR models tested in cross-validation achieve 70%-80% balanced accuracies with constraints on tested compounds. Cross validation of data fusion RASARs show balanced accuracies in the 80%-95% range across 9 health hazards with no constraints on tested compounds.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
1,500 scientists lift the lid on reproducibility
Baker, M. (2016) · Nature · doi:10.1038/533452a · Cited by 4,209
Toxicology for the twenty-first century
Hartung, T. (2009) · Nature · doi:10.1038/460208a · Cited by 661
Self-citationAssessing skin sensitization hazard in mice and men using non-animal test methods
Urbisch, D., Mehling, A., Guth, K., Ramirez, T., Honarvar, N., Kolle, S., Landsiedel, R., Jaworska, J., Kern, P. S., Gerberick, F., et al. (2015) · Regulatory Toxicology and Pharmacology · doi:10.1016/j.yrtph.2014.12.008 · Cited by 398
Chemical regulators have overreached
Hartung, T., & Rovida, C. (2009) · Nature · doi:10.1038/4601080a · Cited by 255
Self-citationA roadmap for the development of alternative (non-animal) methods for systemic toxicity testing
Basketter, D. (2012) · ALTEX · doi:10.14573/altex.2012.1.003 · Cited by 225
Toward Good Read-Across Practice (GRAP) guidance
Ball, N. (2016) · ALTEX · doi:10.14573/altex.1601251 · Cited by 205
Look back in anger – what clinical studies tell us about preclinical work
Hartung, T. (2013) · ALTEX · doi:10.14573/altex.2013.3.275 · Cited by 200
Self-citationThe European Union’s REACH regulation: a review of its history and requirements
Williams, E. S., Panko, J., & Paustenbach, D. J. (2009) · Critical Reviews in Toxicology · doi:10.1080/10408440903036056 · Cited by 195
Green Toxicology: a strategy for sustainable chemical and material development
Crawford, S. E., Härtung, T., Hollert, H., Mathes, B., van Ravenzwaay, B., Steger‐Hartmann, T., Studer, C., & Krug, H. F. (2017) · Environmental Sciences Europe · doi:10.1186/s12302-017-0115-z · Cited by 145
Read-across approaches - misconceptions, promises and challenges ahead
Patlewicz, G. Y., Ball, N., Becker, R. A., Booth, E. D., Cronin, M., Kroese, D., Steup, D., van Ravenzwaay, B., & Hartung, T. (2014) · ALTEX · doi:10.14573/altex.1410071 · Cited by 136
Self-citationUse of category approaches, read-across and (Q)SAR: General considerations
Patlewicz, G. Y., Ball, N. S., Booth, E. D., Hulzebos, E., Zvinavashe, E., & Hennes, C. (2013) · Regulatory Toxicology and Pharmacology · doi:10.1016/j.yrtph.2013.06.002 · Cited by 136
Luechtefeld, T., Maertens, A., Russo, D. P., Rovida, C., Zhu, H., & Hartung, T. (2016) · ALTEX · doi:10.14573/altex.1510053 · Cited by 132
Self-citationMaking big sense from big data in toxicology by read-across
Härtung, T. (2016) · ALTEX · doi:10.14573/altex.1603091 · Cited by 120
Food for thought … on in silico methods in toxicology
Härtung, T., & Hoffmann, S. (2009) · ALTEX · doi:10.14573/altex.2009.3.155 · Cited by 119
Adriaens, E., Barroso, J., Eskes, C., Hoffmann, S., McNamee, P. M., Alépée, N., Bessou‐Touya, S., Smedt, A. D., Wever, B. D., Pfannenbecker, U., et al. (2013) · Archives of Toxicology · doi:10.1007/s00204-013-1156-8 · Cited by 117
Food for thought ... on animal tests
Härtung, T. (2008) · ALTEX · doi:10.14573/altex.2008.1.3 · Cited by 113
Patlewicz, G. Y., & Fitzpatrick, J. M. (2015) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.5b00388 · Cited by 110
Supporting read-across using biological data
Zhu, H., Bouhifd, M., Donley, E., Egnash, L., Kleinstreuer, N., Kroese, E. D., Liu, Z., Luechtefeld, T., Palmer, J., Pamies, D., et al. (2016) · ALTEX · doi:10.14573/altex.1601252 · Cited by 106
Self-citationShah, I., Liu, J., Judson, R., Thomas, R. S., & Patlewicz, G. Y. (2016) · Regulatory Toxicology and Pharmacology · doi:10.1016/j.yrtph.2016.05.008 · Cited by 102
Big-data and machine learning to revamp computational toxicology and its use in risk assessment
Luechtefeld, T., Rowlands, C., & Härtung, T. (2018) · Toxicology Research · doi:10.1039/c8tx00051d · Cited by 98
Self-citationFood for thought... on the economics of animal testing
Bottini, A. (2009) · ALTEX · doi:10.14573/altex.2009.1.3 · Cited by 93
Food for thought ... on alternative methods for cosmetics safety testing
Härtung, T. (2008) · ALTEX · doi:10.14573/altex.2008.3.147 · Cited by 90
3S - Systematic, systemic, and systems biology and toxicology
Smirnova, L., Kleinstreuer, N., Corvi, R., Levchenko, A., Fitzpatrick, S. C., & Hartung, T. (2018) · ALTEX · doi:10.14573/altex.1804051 · Cited by 87
Self-citationLuechtefeld, T., Maertens, A., Russo, D. P., Rovida, C., Zhu, H., & Hartung, T. (2016) · ALTEX · doi:10.14573/altex.1510052 · Cited by 81
Self-citationHoffmann, S. (2015) · ALTEX · doi:10.14573/altex.1505051 · Cited by 80
Hoffmann, S., & Härtung, T. (2005) · Toxicological Sciences · doi:10.1093/toxsci/kfi099 · Cited by 77
Hoffmann, S., Kinsner‐Ovaskainen, A., Prieto, P., Mangelsdorf, I., Bieler, C. A., & Cole, T. (2010) · Regulatory Toxicology and Pharmacology · doi:10.1016/j.yrtph.2010.08.004 · Cited by 76
Food for thought … on alternative methods for chemical safety testing
Härtung, T. (2010) · ALTEX · doi:10.14573/altex.2010.1.3 · Cited by 72
Computational approaches to chemical hazard assessment
Luechtefeld, T., & Hartung, T. (2017) · ALTEX · doi:10.14573/altex.1710141 · Cited by 67
Self-citationAnalysis of publically available skin sensitization data from REACH registrations 2008-2014
Luechtefeld, T., Maertens, A., Russo, D. P., Rovida, C., Zhu, H., & Hartung, T. (2016) · ALTEX · doi:10.14573/altex.1510055 · Cited by 63
Self-citationMaertens, A. (2014) · ALTEX · doi:10.14573/altex.1406181 · Cited by 61
Analysis of public oral toxicity data from REACH registrations 2008-2014
Luechtefeld, T., Maertens, A., Russo, D. P., Rovida, C., Zhu, H., & Hartung, T. (2016) · ALTEX · doi:10.14573/altex.1510054 · Cited by 58
Self-citationOpinion versus evidence for the need to move away from animal testing
Härtung, T. (2017) · ALTEX · doi:10.14573/altex.1703291 · Cited by 53
Härtung, T. (2017) · ALTEX · doi:10.14573/altex.1707011 · Cited by 51
How are reproductive toxicity and developmental toxicity addressed in REACH dossiers?
Rovida, C. (2011) · ALTEX · doi:10.14573/altex.2011.4.273 · Cited by 45
Kolle, S. N., Kanďárová, H., Wareing, B., van Ravenzwaay, B., & Landsiedel, R. (2011) · Alternatives to Laboratory Animals · doi:10.1177/026119291103900410 · Cited by 43
Green Toxicology—Know Early About and Avoid Toxic Product Liabilities
Maertens, A., & Härtung, T. (2017) · Toxicological Sciences · doi:10.1093/toxsci/kfx243 · Cited by 41
Rebooting the generally recognized as safe (GRAS) approach for food additive safety in the US
Härtung, T. (2018) · ALTEX · doi:10.14573/altex.1712181 · Cited by 32
Lessons learned, challenges, and opportunities: The U.S. Endocrine Disruptor Screening Program
Juberg, D. R., Borghoff, S. J., Becker, R. A., Casey, W., Härtung, T., Holsapple, M. P., Marty, M. S., Mihaich, E. M., Kraak, G. V. D., Wade, M. G., et al. (2014) · ALTEX · doi:10.14573/altex.1309171 · Cited by 30
The Threshold of Toxicological Concern for prenatal developmental toxicity in rats and rabbits
van Ravenzwaay, B., Jiang, X., Luechtefeld, T. H., & Härtung, T. (2017) · Regulatory Toxicology and Pharmacology · doi:10.1016/j.yrtph.2017.06.008 · Cited by 29
Self-citationThe need for strategic development of safety sciences
Busquet, F., & Hartung, T. (2017) · ALTEX · doi:10.14573/altex.1701031 · Cited by 27
Self-citationE-cigarettes and the need and opportunities for alternatives to animal testing
Härtung, T. (2016) · ALTEX · doi:10.14573/altex.1606291 · Cited by 22
REACH and CLP. Its Role in Regulatory Toxicology
Aulmann, W., Hovest, M. G., Lemm, D., & Pechacek, N. (2020) · Springer eBooks · doi:10.1007/978-3-642-36206-4_92-2 · Cited by 1
Cited by
High-performance medicine: the convergence of human and artificial intelligence
Topol, E. J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0300-7 · Cited by 10,450
Artificial intelligence to deep learning: machine intelligence approach for drug discovery
Gupta, R., Srivastava, D., Sahu, M., Tiwari, S., Ambasta, R. K., & Kumar, P. (2021) · Molecular Diversity · doi:10.1007/s11030-021-10217-3 · Cited by 1,473
“Recently, other ML-based tools such as SPIDER [342] and read-across structure–activity relationships (RASAR) [343] were developed, which are capable of analyzing β-lapachone targets and linking molecular structures and toxic properties of an unknown compound, respectively.”
MethodArtificial intelligence in drug development: Present status and future prospects
Mak, K.-K., & Pichika, M. R. (2019) · Drug Discovery Today · doi:10.1016/j.drudis.2018.11.014 · Cited by 1,018
Limitations of Animal Studies for Predicting Toxicity in Clinical Trials
Van Norman, G. A. (2019) · JACC: Basic to Translational Science · doi:10.1016/j.jacbts.2019.10.008 · Cited by 732
Date, M. S., O’Brien, D., Botelho, D. J., Schultz, T. W., Liebler, D. C., Penning, T. M., & Salvito, D. T. (2020) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.9b00518 · Cited by 705
Metadata
- Authors
- Luechtefeld, T., Marsh, D., Rowlands, C., & Hartung, T.
- Venue
- Toxicological Sciences
- Publisher
- Oxford University Press (OUP)
- Published
- 2018-07-11
- Volume
- 165
- Issue
- 1
- Pages
- 198-212
- ISSN
- 1096-0929 (ISSN-L)
- 1096-6080
- OpenAlex
- W2822962393
- Cited by
- 327
- References
- 44
- FWCI
- 22.19
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.